© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 7827
    Prev
    Next
    INDEX
    Explanations

    referee decisions and penalties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    een
    0.82
    ovan
    0.78
    elle
    0.73
    %.
    0.71
     pounds
    0.71
     nails
    0.71
    ih
    0.70
    inh
    0.70
     faithfully
    0.69
    begin
    0.68
    POSITIVE LOGITS
     Enforcement
    0.88
     Referee
    0.88
     Handball
    0.85
    AllRef
    0.85
    并没有
    0.83
     Fonbet
    0.82
    ผู้ชมในสนาม
    0.80
     Kyrgios
    0.80
    ટ
    0.78
     Dade
    0.78
    Activations Density 0.005%

    No Known Activations